Automated summary
Evaluates API documentation quality by checking it against the actual implementation: endpoint coverage, accurate parameters and responses, usable examples, and the presence of a machine-readable spec.
Strengths
- Structured rubric covering completeness, accuracy, developer experience, and machine-readable specs
- Explicit docs-vs-code comparison that surfaces phantom parameters and undocumented ones
- Checks response examples against real response shapes and requires error codes to explain cause and fix
- Actionable output with an overall rating, list of undocumented endpoints, and concrete recommendations
Limitations
- Assumes the agent can see both the docs and the source code for the accuracy pass
- Verifies that an OpenAPI/GraphQL/protobuf spec exists and is in sync, but does not lint or validate the schema itself
- No editorial or writing-style guidance beyond the listed quality criteria
Use it during an API docs review before publishing, or after endpoint changes when documentation and code need to be realigned.
Avoid it for writing documentation from scratch or for reviewing non-technical product documentation outside an API context.
Security analysis
SafeThis is a pure instructional checklist for reviewing API documentation quality. It declares no tools, executes no code, touches no network or filesystem, and contains no destructive, exfiltrating, or obfuscated instructions. The only implicit action is reading documentation and comparing it to source code, which is benign review work.
No concerns found
How this analysis is madeExamples
Review the API documentation in docs/api/ against the route handlers in src/routes/. Rate its quality, list undocumented endpoints, flag any parameter or response examples that don't match the code, and give me concrete fixes.Check whether our openapi.yaml is kept in sync with the implementation. Flag endpoints, parameters, or status codes that appear in one but not the other.Pretend you're a developer integrating with our API for the first time using only the docs. Tell me where the quickstart breaks down, which examples lack a response, and which error codes are unexplained.name: api-documentation-review description: Evaluate API documentation quality — completeness, accuracy, examples, and developer experience.
Instructions
You are evaluating the quality of API documentation. Good API docs enable developers to integrate without reading source code.
Completeness Check
For every public endpoint or method:
- Is the endpoint documented?
- Are request parameters documented (path, query, header, body) with types and required/optional status?
- Is the response structure documented for all status codes (success AND error)?
- Are authentication requirements stated?
- Are rate limits documented?
Accuracy Check
- Compare documentation against the actual implementation.
- Flag documented parameters that do not exist in the code.
- Flag undocumented parameters that exist in the code.
- Flag response examples that do not match the actual response shape.
- Flag documented behavior that contradicts the implementation.
Developer Experience
- Are there working examples for common use cases?
- Do examples include request AND response (not just one side)?
- Is there a "quickstart" section that gets a developer from zero to a successful API call?
- Are error responses documented with explanations of what causes each error and how to fix it?
- Is the documentation searchable and well-organized?
Machine-Readable Specs
- Verify an OpenAPI (Swagger), GraphQL schema, or protobuf definition exists.
- Check that the spec is auto-generated or kept in sync with the code.
- Flag specs that are manually maintained and likely to drift.
- Verify the spec is published and accessible to consumers.
Output
- Rate documentation quality: Excellent / Adequate / Incomplete / Missing.
- List undocumented endpoints.
- List inaccuracies between docs and implementation.
- Provide specific improvement recommendations.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/api-documentation-review-mrzxuqgz' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/api-documentation-review-mrzxuqgz/download' --output '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md.part' && mv '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md.part' '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md' && test -s '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/api-documentation-review' && cp -R '.skill-downloads/api-documentation-review-mrzxuqgz' '.claude/skills/api-documentation-review'Cursor
test -f '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md' && test -s '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/api-documentation-review' && cp -R '.skill-downloads/api-documentation-review-mrzxuqgz' '.cursor/skills/api-documentation-review'Codex
test -f '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md' && test -s '.skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/api-documentation-review' && cp -R '.skill-downloads/api-documentation-review-mrzxuqgz' '.agents/skills/api-documentation-review'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/api-documentation-review-mrzxuqgz'openskills read 'api-documentation-review-mrzxuqgz'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/api-documentation-review-mrzxuqgz/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.